We study inventory control policies for pharmaceutical supply chains, addressing challenges such as perishability, yield uncertainty, and non-stationary demand, combined with batching constraints, lead times, and lost sales. Collaborating with Bristol-Myers Squibb (BMS), we develop a realistic case study incorporating these factors and benchmark three policies--order-up-to (OUT), projected inventory level (PIL), and deep reinforcement learning (DRL) using the proximal policy optimization (PPO) algorithm--against a BMS baseline based on human expertise. We derive and validate bounds-based procedures for optimizing OUT and PIL policy parameters and propose a methodology for estimating projected inventory levels, which are also integrated into the DRL policy with demand forecasts to improve decision-making under non-stationarity. Compared to a human-driven policy, which avoids lost sales through higher holding costs, all three implemented policies achieve lower average costs but exhibit greater cost variability. While PIL demonstrates robust and consistent performance, OUT struggles under high lost sales costs, and PPO excels in complex and variable scenarios but requires significant computational effort. The findings suggest that while DRL shows potential, it does not outperform classical policies in all numerical experiments, highlighting 1) the need to integrate diverse policies to manage pharmaceutical challenges effectively, based on the current state-of-the-art, and 2) that practical problems in this domain seem to lack a single policy class that yields universally acceptable performance.

Policy gradient methods are widely used in reinforcement learning. Yet, the nonconvexity of policy optimization imposes significant challenges in understanding the global convergence of policy gradient methods. For a class of finite-horizon Markov Decision Processes (MDPs) with general state and action spaces, we develop a framework that provides a set of easily verifiable assumptions to ensure the Kurdyka-Lojasiewicz (KL) condition of the policy optimization. Leveraging the KL condition, policy gradient methods converge to the globally optimal policy with a non-asymptomatic rate despite nonconvexity. Our results find applications in various control and operations models, including entropy-regularized tabular MDPs, Linear Quadratic Regulator (LQR) problems, stochastic inventory models, and stochastic cash balance problems, for which we show an $\epsilon$-optimal policy can be obtained using a sample size in $\tilde{\mathcal{O}}(\epsilon^{-1})$ and polynomial in terms of the planning horizon by stochastic policy gradient methods. Our result establishes the first sample complexity for multi-period inventory systems with Markov-modulated demands and stochastic cash balance problems in the literature.

Stochastic gradient descent (SGD) has proven effective in solving many inventory control problems with demand learning. However, it often faces the pitfall of an infeasible target inventory level that is lower than the current inventory level. Several recent works (e.g., Huh and Rusmevichientong (2009), Shi et al.(2016)) are successful to resolve this issue in various inventory systems. However, their techniques are rather sophisticated and difficult to be applied to more complicated scenarios such as multi-product and multi-constraint inventory systems. In this paper, we address the infeasible-target-inventory-level issue from a new technical perspective -- we propose a novel minibatch-SGD-based meta-policy. Our meta-policy is flexible enough to be applied to a general inventory systems framework covering a wide range of inventory management problems with myopic clairvoyant optimal policy. By devising the optimal minibatch scheme, our meta-policy achieves a regret bound of $\mathcal{O}(\sqrt{T})$ for the general convex case and $\mathcal{O}(\log T)$ for the strongly convex case. To demonstrate the power and flexibility of our meta-policy, we apply it to three important inventory control problems: multi-product and multi-constraint systems, multi-echelon serial systems, and one-warehouse and multi-store systems by carefully designing application-specific subroutines.We also conduct extensive numerical experiments to demonstrate that our meta-policy enjoys competitive regret performance, high computational efficiency, and low variances among a wide range of applications.

We consider a stochastic lost-sales inventory control system with a lead time $L$ over a planning horizon $T$. Supply is uncertain, and is a function of the order quantity (due to random yield/capacity, etc). We aim to minimize the $T$-period cost, a problem that is known to be computationally intractable even under known distributions of demand and supply. In this paper, we assume that both the demand and supply distributions are unknown and develop a computationally efficient online learning algorithm. We show that our algorithm achieves a regret (i.e. the performance gap between the cost of our algorithm and that of an optimal policy over $T$ periods) of $O(L+\sqrt{T})$ when $L\geq\log(T)$. We do so by 1) showing our algorithm cost is higher by at most $O(L+\sqrt{T})$ for any $L\geq 0$ compared to an optimal constant-order policy under complete information (a well-known and widely-used algorithm) and 2) leveraging its known performance guarantee from the existing literature. To the best of our knowledge, a finite-sample $O(\sqrt{T})$ (and polynomial in $L$) regret bound when benchmarked against an optimal policy is not known before in the online inventory control literature. A key challenge in this learning problem is that both demand and supply data can be censored; hence only truncated values are observable. We circumvent this challenge by showing that the data generated under an order quantity $q^2$ allows us to simulate the performance of not only $q^2$ but also $q^1$ for all $q^1

In this paper we address the problem of learning and backtesting inventory control policies in the presence of general arrival dynamics -- which we term as a quantity-over-time arrivals model (QOT). We also allow for order quantities to be modified as a post-processing step to meet vendor constraints such as order minimum and batch size constraints -- a common practice in real supply chains. To the best of our knowledge this is the first work to handle either arbitrary arrival dynamics or an arbitrary downstream post-processing of order quantities. Building upon recent work (Madeka et al., 2022) we similarly formulate the periodic review inventory control problem as an exogenous decision process, where most of the state is outside the control of the agent. Madeka et al. (2022) show how to construct a simulator that replays historic data to solve this class of problem. In our case, we incorporate a deep generative model for the arrivals process as part of the history replay. By formulating the problem as an exogenous decision process, we can apply results from Madeka et al. (2022) to obtain a reduction to supervised learning. Finally, we show via simulation studies that this approach yields statistically significant improvements in profitability over production baselines. Using data from an ongoing real-world A/B test, we show that Gen-QOT generalizes well to off-policy data.

We study multi-product inventory control problems where a manager makes sequential replenishment decisions based on partial historical information in order to minimize its cumulative losses. Our motivation is to consider general demands, losses and dynamics to go beyond standard models which usually rely on newsvendor-type losses, fixed dynamics, and unrealistic i.i.d. demand assumptions. We propose MaxCOSD, an online algorithm that has provable guarantees even for problems with non-i.i.d. demands and stateful dynamics, including for instance perishability. We consider what we call non-degeneracy assumptions on the demand process, and argue that they are necessary to allow learning.

This work provides a Deep Reinforcement Learning approach to solving a periodic review inventory control system with stochastic vendor lead times, lost sales, correlated demand, and price matching. While this dynamic program has historically been considered intractable, our results show that several policy learning approaches are competitive with or outperform classical methods. In order to train these algorithms, we develop novel techniques to convert historical data into a simulator. On the theoretical side, we present learnability results on a subclass of inventory control problems, where we provide a provable reduction of the reinforcement learning problem to that of supervised learning. On the algorithmic side, we present a model-based reinforcement learning procedure (Direct Backprop) to solve the periodic review inventory control problem by constructing a differentiable simulator. Under a variety of metrics Direct Backprop outperforms model-free RL and newsvendor baselines, in both simulations and real-world deployments.

The tech giant recently filed a patent for a concept device that's equipped with a conveyor belt capable of sorting and transferring items. It could help Amazon tackle many problems related to delays and inefficiency in traditional warehouses. Amazon filed a patent for a concept device that's equipped with a conveyor belt capable of sorting and transferring items. The contraption includes two separate robotic devices that each require separate controllers that can communicate back and forth. A controller for the first device communicates with a controller for the second device, sending signals as to where the robotic instrument should go next.